Anomaly detection in medical images is an important yet challenging task due to the diversity of possible anomalies and the practical impossibility of collecting comprehensively annotated data sets. In this work, we tackle unsupervised medical anomaly detection proposing a modernized autoencoder-based framework, the Q-Former Autoencoder, that leverages state-of-the-art pretrained vision foundation models, such as DINO, DINOv2 and Masked Autoencoder. Instead of training encoders from scratch, we directly utilize frozen vision foundation models as feature extractors, enabling rich, multi-stage, high-level representations without domain-specific fine-tuning. We propose the usage of the Q-Former architecture as the bottleneck, which enables the control of the length of the reconstruction sequence, while efficiently aggregating multiscale features. Additionally, we incorporate a perceptual loss computed using features from a pretrained Masked Autoencoder, guiding the reconstruction towards semantically meaningful structures. Our framework is evaluated on four diverse medical anomaly detection benchmarks, achieving state-of-the-art results on BraTS2021, RESC, and RSNA. Our results highlight the potential of vision foundation model encoders, pretrained on natural images, to generalize effectively to medical image analysis tasks without further fine-tuning. We release the code and models at https://github.com/emirhanbayar/QFAE.

In the medical image analysis field, precise quantification of curve tortuosity plays a critical role in the auxiliary diagnosis and pathological assessment of various diseases. In this study, we propose a novel framework for tortuosity quantification and demonstrate its effectiveness through the evaluation of meibomian gland atrophy uniformity,serving as a representative application scenario. We introduce an information entropy-based tortuosity quantification framework that integrates probability modeling with entropy theory and incorporates domain transformation of curve data. Unlike traditional methods such as curvature or arc-chord ratio, this approach evaluates the tortuosity of a target curve by comparing it to a designated reference curve. Consequently, it is more suitable for tortuosity assessment tasks in medical data where biologically plausible reference curves are available, providing a more robust and objective evaluation metric without relying on idealized straight-line comparisons. First, we conducted numerical simulation experiments to preliminarily assess the stability and validity of the method. Subsequently, the framework was applied to quantify the spatial uniformity of meibomian gland atrophy and to analyze the difference in this uniformity between \textit{Demodex}-negative and \textit{Demodex}-positive patient groups. The results demonstrated a significant difference in tortuosity-based uniformity between the two groups, with an area under the curve of 0.8768, sensitivity of 0.75, and specificity of 0.93. These findings highlight the clinical utility of the proposed framework in curve tortuosity analysis and its potential as a generalizable tool for quantitative morphological evaluation in medical diagnostics.

Dual-energy X-ray Computed Tomography (DECT) constitutes an advanced technology which enables automatic decomposition of materials in clinical images without manual segmentation using the dependency of the X-ray linear attenuation with energy. However, most methods perform material decomposition in the image domain as a post-processing step after reconstruction but this procedure does not account for the beam-hardening effect and it results in sub-optimal results. In this work, we propose a deep learning procedure called Dual-Energy Decomposition Model-based Diffusion (DEcomp-MoD) for quantitative material decomposition which directly converts the DECT projection data into material images. The algorithm is based on incorporating the knowledge of the spectral DECT model into the deep learning training loss and combining a score-based denoising diffusion learned prior in the material image domain. Importantly the inference optimization loss takes as inputs directly the sinogram and converts to material images through a model-based conditional diffusion model which guarantees consistency of the results. We evaluate the performance with both quantitative and qualitative estimation of the proposed DEcomp-MoD method on synthetic DECT sinograms from the low-dose AAPM dataset. Finally, we show that DEcomp-MoD outperform state-of-the-art unsupervised score-based model and supervised deep learning networks, with the potential to be deployed for clinical diagnosis.

Medical image segmentation is a complex and challenging task, which aims to accurately segment various structures or abnormal regions in medical images. However, obtaining accurate segmentation results is difficult because of the great uncertainty in the shape, location, and scale of the target region. To address these challenges, we propose a higher-order spatial interaction framework with dual cross global efficient attention (DGEAHorNet), which employs a neural network architecture based on recursive gate convolution to adequately extract multi-scale contextual information from images. Specifically, a Dual Cross-Attentions (DCA) is added to the skip connection that can effectively blend multi-stage encoder features and narrow the semantic gap. In the bottleneck stage, global channel spatial attention module (GCSAM) is used to extract image global information. To obtain better feature representation, we feed the output from the GCSAM into the multi-branch dense layer (SENetV2) for excitation. Furthermore, we adopt Depthwise Over-parameterized Convolutional Layer (DO-Conv) in order to replace the common convolutional layer in the input and output part of our network, then add Efficient Attention (EA) to diminish computational complexity and enhance our model's performance. For evaluating the effectiveness of our proposed DGEAHorNet, we conduct comprehensive experiments on four publicly-available datasets, and achieving 0.9320, 0.9337, 0.9312 and 0.7799 in Dice similarity coefficient on ISIC2018, ISIC2017, CVC-ClinicDB and HRF respectively. Our results show that DGEAHorNet has better performance compared with advanced methods. The code is publicly available at https://github.com/penghaixin/mymodel .


Clinical drivers for real-time head and neck (H&N) tumor tracking during radiation therapy (RT) are accounting for motion caused by changes to the immobilization mask fit, and to reduce mask-related patient distress by replacing the masks with patient motion management methods. The purpose of this paper is to investigate a deep learning-based method to segment H&N tumors in patient kilovoltage (kV) x-ray images to enable real-time H&N tumor tracking during RT.
Approach: An ethics-approved clinical study collected data from 17 H&N cancer patients undergoing conventional H&N RT. For each patient, personalized conditional Generative Adversarial Networks (cGANs) were trained to segment H&N tumors in kV x-ray images. Network training data were derived from each patient's planning CT and contoured gross tumor volumes (GTV). For each training epoch, the planning CT and GTV were deformed and forward projected to create the training dataset. The testing data consisted of kV x-ray images used to reconstruct the pre-treatment CBCT volume for the first, middle and end fractions. The ground truth tumor locations were derived by deformably registering the planning CT to the pre-treatment CBCT and then deforming the GTV and forward projecting the deformed GTV. The generated cGAN segmentations were compared to ground truth tumor segmentations using the absolute magnitude of the centroid error and the mean surface distance (MSD) metrics.
Main Results:
The centroid error for the nasopharynx (n=4), oropharynx (n=9) and larynx (n=4) patients was 1.5±0.9mm, 2.4±1.6mm, 3.5±2.2mm respectively and the MSD was 1.5±0.3mm, 1.9±0.9mm and 2.3±1.0mm respectively. There was a weak correlation between the centroid error and the LR tumor location (r=0.41), which was higher for oropharynx patients (r=0.77).
Significance: The paper reports on markerless H&N tumor detection accuracy using kV images. Accurate tracking of H&N tumors can enable more precise RT leading to mask-free RT enabling better patient outcomes.&#xD.

This study aims to explore a novel approach for predicting cervical lymph node metastasis (CLNM) and pathological subtypes in oral squamous cell carcinoma (OSCC) by comparing deep learning (DL) and habitat analysis models based on contrast-enhanced CT (CECT). A retrospective analysis was conducted using CECT images from patients diagnosed with OSCC via paraffin pathology at the Second Affiliated Hospital of Dalian Medical University. All patients underwent primary tumor resection and cervical lymph node dissection, with a total of 132 cases included. A DL model was developed by analysing regions of interest (ROIs) in the CECT images using a convolutional neural network (CNN). For habitat analysis, the ROI images were segmented into 3 regions using K-means clustering, and features were selected through a fully connected neural network (FCNN) to build the model. A separate clinical model was constructed based on nine clinical features, including age, gender, and tumor location. Using LNM and pathological subtypes as endpoints, the predictive performance of the clinical model, DL model, habitat analysis model, and a combined clinical + habitat model was evaluated using confusion matrices and receiver operating characteristic (ROC) curves. For LNM prediction, the combined clinical + habitat model achieved an area under the ROC curve (AUC) of 0.97. For pathological subtype prediction, the AUC was 0.96. The DL model yielded an AUC of 0.83 for LNM prediction and 0.91 for pathological subtype classification. The clinical model alone achieved an AUC of 0.94 for predicting LNM. The integrated habitat-clinical model demonstrates improved predictive performance. Combining habitat analysis with clinical features offers a promising approach for the prediction of oral cancer. The habitat-clinical integrated model may assist clinicians in performing accurate preoperative prognostic assessments in patients with oral cancer.

The emergence of Vision Transformers (ViTs) has revolutionized computer vision, yet their effectiveness compared to traditional Convolutional Neural Networks (CNNs) in medical imaging remains under-explored. This study presents a comprehensive comparative analysis of CNN and ViT architectures across three critical medical imaging tasks: chest X-ray pneumonia detection, brain tumor classification, and skin cancer melanoma detection. We evaluated four state-of-the-art models - ResNet-50, EfficientNet-B0, ViT-Base, and DeiT-Small - across datasets totaling 8,469 medical images. Our results demonstrate task-specific model advantages: ResNet-50 achieved 98.37% accuracy on chest X-ray classification, DeiT-Small excelled at brain tumor detection with 92.16% accuracy, and EfficientNet-B0 led skin cancer classification at 81.84% accuracy. These findings provide crucial insights for practitioners selecting architectures for medical AI applications, highlighting the importance of task-specific architecture selection in clinical decision support systems.

BackgroundAdvancements in imaging technology, alongside increasing longevity and co-morbidities, have led to heightened demand for diagnostic radiology services. However, there is a shortfall in radiology and radiography staff to acquire, read and report on such imaging examinations. Artificial intelligence (AI) has been identified, notably by AI developers, as a potential solution to impact positively the workload of radiology services for diagnostics to address this staffing shortfall. MethodsA rapid review complemented with data from interviews with UK radiology service stakeholders was undertaken. ArXiv, Cochrane Library, Embase, Medline and Scopus databases were searched for publications in English published between 2007 and 2022. Following screening 110 full texts were included. Interviews with 15 radiology service managers, clinicians and academics were carried out between May and September 2022. ResultsMost literature was published in 2021 and 2022 with a distinct focus on AI for diagnostics of lung and chest disease (n = 25) notably COVID-19 and respiratory system cancers, closely followed by AI for breast screening (n = 23). AI contribution to streamline the workload of radiology services was categorised as autonomous, augmentative and assistive contributions. However, percentage estimates, of workload reduction, varied considerably with the most significant reduction identified in national screening programmes. AI was also recognised as aiding radiology services through providing second opinion, assisting in prioritisation of images for reading and improved quantification in diagnostics. Stakeholders saw AI as having the potential to remove some of the laborious work and contribute service resilience. ConclusionsThis review has shown there is limited data on real-world experiences from radiology services for the implementation of AI in clinical production. Autonomous, augmentative and assistive AI can, as noted in the article, decrease workload and aid reading and reporting, however the governance surrounding these advancements lags.

The rapid advancement of artificial intelligence (AI) in healthcare has accelerated innovations in medical algorithms, yet its broader adoption faces critical ethical and technical barriers. A key challenge lies in algorithmic bias stemming from heterogeneous medical data across institutions, equipment, and workflows, which may perpetuate disparities in AI-driven diagnoses and exacerbate inequities in patient care. While AI's ability to extract deep features from large-scale data offers transformative potential, its effectiveness heavily depends on standardized, high-quality datasets. Current standardization gaps not only limit model generalizability but also raise concerns about reliability and fairness in real-world clinical settings, particularly for marginalized populations. Addressing these urgent issues, this paper proposes an ethical AI framework centered on a novel self-supervised medical image standardization method. By integrating self-supervised image style conversion, channel attention mechanisms, and contrastive learning-based loss functions, our approach enhances structural and style consistency in diverse datasets while preserving patient privacy through decentralized learning paradigms. Experiments across multi-institutional medical image datasets demonstrate that our method significantly improves AI generalizability without requiring centralized data sharing. By bridging the data standardization gap, this work advances technical foundations for trustworthy AI in healthcare.

In computed tomography (CT), achieving high image quality while minimizing radiation exposure remains a key clinical challenge. This paper presents CAPRI-CT, a novel causal-aware deep learning framework for Causal Analysis and Predictive Reasoning for Image Quality Optimization in CT imaging. CAPRI-CT integrates image data with acquisition metadata (such as tube voltage, tube current, and contrast agent types) to model the underlying causal relationships that influence image quality. An ensemble of Variational Autoencoders (VAEs) is employed to extract meaningful features and generate causal representations from observational data, including CT images and associated imaging parameters. These input features are fused to predict the Signal-to-Noise Ratio (SNR) and support counterfactual inference, enabling what-if simulations, such as changes in contrast agents (types and concentrations) or scan parameters. CAPRI-CT is trained and validated using an ensemble learning approach, achieving strong predictive performance. By facilitating both prediction and interpretability, CAPRI-CT provides actionable insights that could help radiologists and technicians design more efficient CT protocols without repeated physical scans. The source code and dataset are publicly available at https://github.com/SnehaGeorge22/capri-ct.